elib
DLR-Header
DLR-Logo -> http://www.dlr.de
DLR Portal Home | Imprint | Privacy Policy | Contact | Deutsch
Fontsize: [-] Text [+]

Can a Deep Network Understand the Land Cover Across Sensors?

Huang, Zhongling and Dumitru, Corneliu Octavian and Pang, Zhonghe and Le, Bin and Datcu, Mihai (2019) Can a Deep Network Understand the Land Cover Across Sensors? In: 2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS), pp. 1-4. IGARSS 2019, 28.7.–2.8.2019, Yokohama, Japan.

[img] PDF
971kB

Official URL: https://igarss2019.org/Papers/ViewPapers.asp?PaperNum=3798

Abstract

Deep learning algorithms are widely used in remote sensing image scene understanding. Generally, a large-scale annotated dataset is essential to train a deep neural network for classification. In practical terms, however, a large amount of unknown remote sensing images obtained from different sensors need to be understood which may vary from resolution, geolocation and imaging conditions compared with annotated datasets. In this paper, an unsupervised domain adaptation framework based on ResNet-18 is presented to transfer the knowledge of an existing annotated land cover dataset to other remote sensing data, decreasing the discrepancy among images across sensors. The results show a significant improvement in scene understanding of new remote sensing images.

Item URL in elib:https://elib.dlr.de/130278/
Document Type:Conference or Workshop Item (Poster)
Title:Can a Deep Network Understand the Land Cover Across Sensors?
Authors:
AuthorsInstitution or Email of AuthorsAuthors ORCID iD
Huang, Zhonglinghuangzhongling15 (at) mails.ucas.ac.cnUNSPECIFIED
Dumitru, Corneliu OctavianCorneliu.Dumitru (at) dlr.deUNSPECIFIED
Pang, ZhongheInstitute of Geology and Geophysics, CASUNSPECIFIED
Le, BinChinese Academy of ScienceUNSPECIFIED
Datcu, MihaiMihai.Datcu (at) dlr.deUNSPECIFIED
Date:January 2019
Journal or Publication Title:2019 IEEE International Geoscience and Remote Sensing Symposium (IGARSS)
Refereed publication:Yes
Open Access:Yes
Gold Open Access:No
In SCOPUS:No
In ISI Web of Science:No
Page Range:pp. 1-4
Status:Published
Keywords:land use classification,remote sensing images, transfer learning, domain adaptation
Event Title:IGARSS 2019
Event Location:Yokohama, Japan
Event Type:international Conference
Event Dates:28.7.–2.8.2019
HGF - Research field:Aeronautics, Space and Transport
HGF - Program:Space
HGF - Program Themes:Earth Observation
DLR - Research area:Raumfahrt
DLR - Program:R EO - Erdbeobachtung
DLR - Research theme (Project):R - Vorhaben hochauflösende Fernerkundungsverfahren
Location: Oberpfaffenhofen
Institutes and Institutions:Remote Sensing Technology Institute > EO Data Science
Deposited By: Karmakar, Chandrabali
Deposited On:02 Dec 2019 14:27
Last Modified:03 Dec 2019 18:36

Repository Staff Only: item control page

Browse
Search
Help & Contact
Information
electronic library is running on EPrints 3.3.12
Copyright © 2008-2017 German Aerospace Center (DLR). All rights reserved.